AI agents call recent to retrieve information from Agent Bus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical message data from a shared message bus without creating, modifying, or deleting anything. However, severity is elevated from 'low' to 'medium' because the tool reads messages 'regardless of recipient'—meaning it can access messages intended for other agents on the same machine.
From the tool's definition Tool description explicitly states 'Read the most recent messages on the bus' with no modification or side effects. The word 'Read' and 'catching up' indicate data retrieval only.
Attacks that exploit this kind of access
Read the most recent messages on the bus regardless of recipient. Useful for catching up. It is categorised as a Read tool in the Agent Bus MCP Server, which means it retrieves data without modifying state.
Register the Agent Bus MCP server in PolicyLayer and add a rule for recent: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Agent Bus. Nothing to install.
recent is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the recent rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for recent. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
recent is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →